INDEX

Explanations

terms related to sets and collections

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 FileReader

-0.56

 SqlParameter

-0.56

hoga

-0.51

isContained

-0.51

MigrationBuilder

-0.51

SharedCtor

-0.50

 QLabel

-0.49

abstractmethod

-0.48

PreAuthorize

-0.48

IBOutlet

-0.45

POSITIVE LOGITS

 consisting

0.94

 consists

0.80

 comprising

0.79

 comprises

0.72

 composed

0.68

набор

0.66

 comprenant

0.66

 comprised

0.65

جموعة

0.65

Série

0.64

Activations Density 0.782%

terms related to sets and collections

No Comments

No Known Activations